MMSE-HR dataset (Multimodal Spontaneous Expression-Heart Rate dataset)

 Background: 

 Recent studies in computer vision have shown that, while practically invisible to a human observer, skin color changes due to blood flow can be captured on face and can be used to estimate heart rate (HR). While considerable progress has been made in the last few years, still many issues remain open. Unlike previous approaches that estimate the HR by processing all the skin pixels inside a fixed region of interest, we introduce a strategy to dynamically select face regions useful for robust HR estimation.

 Technology Overview: 

 Our approach, inspired by recent advances in matrix completion theory, allows us to predict the HR while simultaneously discovering the best regions of the face to use for estimation. This database contains 102 videos of 40 subjects, including 2D facial expression video sequences and the corresponding heart-rate (HR) and blood-pressure (BP) sequences. 

 Advantages: 

• Facial expression annotated for both the occurrence and intensity of facial action units from 2D video by experts in the Facial Action Coding System (FACS).
• Database includes a diverse array of participants.
• Could lead into non-invasive, remote heart rate estimation from a 2D camera for healthcare purposes.